© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 48319
    Prev
    Next
    INDEX
    Explanations

    strengthen or stretch

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    bcywinski/Olmo-3-32B-Base-SAE/saes_allenai_Olmo-3-1125-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    atin
    -0.10
    ical
    -0.09
    ledo
    -0.09
    avier
    -0.09
     impres
    -0.09
    eed
    -0.09
    iah
    -0.08
     Mo
    -0.08
    uess
    -0.08
    ions
    -0.08
    POSITIVE LOGITS
    ngthen
    0.18
    NGTH
    0.15
     stre
    0.13
     stretch
    0.12
     Stretch
    0.11
    stre
    0.11
    /testify
    0.11
     Stre
    0.11
    ighted
    0.10
    ptom
    0.10
    Activations Density 0.032%

    No Known Activations